Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
gaoqiong
lm-evaluation-harness
Commits
60c9c170
Commit
60c9c170
authored
May 29, 2024
by
haileyschoelkopf
Browse files
Merge branch 'main' into inverse-scaling-tasks
parents
4b2d565b
b4cd85d4
Changes
605
Hide whitespace changes
Inline
Side-by-side
Showing
20 changed files
with
149 additions
and
0 deletions
+149
-0
lm_eval/tasks/tmmluplus/default/tmmluplus_physics.yaml
lm_eval/tasks/tmmluplus/default/tmmluplus_physics.yaml
+7
-0
lm_eval/tasks/tmmluplus/default/tmmluplus_politic_science.yaml
...al/tasks/tmmluplus/default/tmmluplus_politic_science.yaml
+7
-0
lm_eval/tasks/tmmluplus/default/tmmluplus_real_estate.yaml
lm_eval/tasks/tmmluplus/default/tmmluplus_real_estate.yaml
+7
-0
lm_eval/tasks/tmmluplus/default/tmmluplus_secondary_physics.yaml
.../tasks/tmmluplus/default/tmmluplus_secondary_physics.yaml
+7
-0
lm_eval/tasks/tmmluplus/default/tmmluplus_statistics_and_machine_learning.yaml
...us/default/tmmluplus_statistics_and_machine_learning.yaml
+7
-0
lm_eval/tasks/tmmluplus/default/tmmluplus_taiwanese_hokkien.yaml
.../tasks/tmmluplus/default/tmmluplus_taiwanese_hokkien.yaml
+7
-0
lm_eval/tasks/tmmluplus/default/tmmluplus_taxation.yaml
lm_eval/tasks/tmmluplus/default/tmmluplus_taxation.yaml
+7
-0
lm_eval/tasks/tmmluplus/default/tmmluplus_technical.yaml
lm_eval/tasks/tmmluplus/default/tmmluplus_technical.yaml
+7
-0
lm_eval/tasks/tmmluplus/default/tmmluplus_three_principles_of_people.yaml
...mluplus/default/tmmluplus_three_principles_of_people.yaml
+7
-0
lm_eval/tasks/tmmluplus/default/tmmluplus_trade.yaml
lm_eval/tasks/tmmluplus/default/tmmluplus_trade.yaml
+7
-0
lm_eval/tasks/tmmluplus/default/tmmluplus_traditional_chinese_medicine_clinical_medicine.yaml
...uplus_traditional_chinese_medicine_clinical_medicine.yaml
+7
-0
lm_eval/tasks/tmmluplus/default/tmmluplus_trust_practice.yaml
...val/tasks/tmmluplus/default/tmmluplus_trust_practice.yaml
+7
-0
lm_eval/tasks/tmmluplus/default/tmmluplus_ttqav2.yaml
lm_eval/tasks/tmmluplus/default/tmmluplus_ttqav2.yaml
+7
-0
lm_eval/tasks/tmmluplus/default/tmmluplus_tve_chinese_language.yaml
...sks/tmmluplus/default/tmmluplus_tve_chinese_language.yaml
+7
-0
lm_eval/tasks/tmmluplus/default/tmmluplus_tve_design.yaml
lm_eval/tasks/tmmluplus/default/tmmluplus_tve_design.yaml
+7
-0
lm_eval/tasks/tmmluplus/default/tmmluplus_tve_mathematics.yaml
...al/tasks/tmmluplus/default/tmmluplus_tve_mathematics.yaml
+7
-0
lm_eval/tasks/tmmluplus/default/tmmluplus_tve_natural_sciences.yaml
...sks/tmmluplus/default/tmmluplus_tve_natural_sciences.yaml
+7
-0
lm_eval/tasks/tmmluplus/default/tmmluplus_veterinary_pathology.yaml
...sks/tmmluplus/default/tmmluplus_veterinary_pathology.yaml
+7
-0
lm_eval/tasks/tmmluplus/default/tmmluplus_veterinary_pharmacology.yaml
.../tmmluplus/default/tmmluplus_veterinary_pharmacology.yaml
+7
-0
lm_eval/tasks/tmmluplus/default/utils.py
lm_eval/tasks/tmmluplus/default/utils.py
+16
-0
No files found.
lm_eval/tasks/tmmluplus/default/tmmluplus_physics.yaml
0 → 100644
View file @
60c9c170
"
dataset_name"
:
"
physics"
"
description"
:
"
以下為物理的單選題,請提供正確答案的選項。
\n\n
"
"
group"
:
"
tmmluplus_STEM"
"
group_alias"
:
"
STEM"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
tmmluplus_physics"
"
task_alias"
:
"
physics"
lm_eval/tasks/tmmluplus/default/tmmluplus_politic_science.yaml
0 → 100644
View file @
60c9c170
"
dataset_name"
:
"
politic_science"
"
description"
:
"
以下為政治的單選題,請提供正確答案的選項。
\n\n
"
"
group"
:
"
tmmluplus_social_sciences"
"
group_alias"
:
"
social
sciences"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
tmmluplus_politic_science"
"
task_alias"
:
"
politic
science"
lm_eval/tasks/tmmluplus/default/tmmluplus_real_estate.yaml
0 → 100644
View file @
60c9c170
"
dataset_name"
:
"
real_estate"
"
description"
:
"
以下為房地產的單選題,請提供正確答案的選項。
\n\n
"
"
group"
:
"
tmmluplus_other"
"
group_alias"
:
"
other"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
tmmluplus_real_estate"
"
task_alias"
:
"
real
estate"
lm_eval/tasks/tmmluplus/default/tmmluplus_secondary_physics.yaml
0 → 100644
View file @
60c9c170
"
dataset_name"
:
"
secondary_physics"
"
description"
:
"
以下為高中物理的單選題,請提供正確答案的選項。
\n\n
"
"
group"
:
"
tmmluplus_STEM"
"
group_alias"
:
"
STEM"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
tmmluplus_secondary_physics"
"
task_alias"
:
"
secondary
physics"
lm_eval/tasks/tmmluplus/default/tmmluplus_statistics_and_machine_learning.yaml
0 → 100644
View file @
60c9c170
"
dataset_name"
:
"
statistics_and_machine_learning"
"
description"
:
"
以下為統計與機器學習的單選題,請提供正確答案的選項。
\n\n
"
"
group"
:
"
tmmluplus_STEM"
"
group_alias"
:
"
STEM"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
tmmluplus_statistics_and_machine_learning"
"
task_alias"
:
"
statistics
and
machine
learning"
lm_eval/tasks/tmmluplus/default/tmmluplus_taiwanese_hokkien.yaml
0 → 100644
View file @
60c9c170
"
dataset_name"
:
"
taiwanese_hokkien"
"
description"
:
"
以下為閩南語的單選題,請提供正確答案的選項。
\n\n
"
"
group"
:
"
tmmluplus_social_sciences"
"
group_alias"
:
"
social
sciences"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
tmmluplus_taiwanese_hokkien"
"
task_alias"
:
"
taiwanese
hokkien"
lm_eval/tasks/tmmluplus/default/tmmluplus_taxation.yaml
0 → 100644
View file @
60c9c170
"
dataset_name"
:
"
taxation"
"
description"
:
"
以下為稅務的單選題,請提供正確答案的選項。
\n\n
"
"
group"
:
"
tmmluplus_humanities"
"
group_alias"
:
"
humanities"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
tmmluplus_taxation"
"
task_alias"
:
"
taxation"
lm_eval/tasks/tmmluplus/default/tmmluplus_technical.yaml
0 → 100644
View file @
60c9c170
"
dataset_name"
:
"
technical"
"
description"
:
"
以下為技術工相關的單選題,請提供正確答案的選項。
\n\n
"
"
group"
:
"
tmmluplus_other"
"
group_alias"
:
"
other"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
tmmluplus_technical"
"
task_alias"
:
"
technical"
lm_eval/tasks/tmmluplus/default/tmmluplus_three_principles_of_people.yaml
0 → 100644
View file @
60c9c170
"
dataset_name"
:
"
three_principles_of_people"
"
description"
:
"
以下為三民主義的單選題,請提供正確答案的選項。
\n\n
"
"
group"
:
"
tmmluplus_social_sciences"
"
group_alias"
:
"
social
sciences"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
tmmluplus_three_principles_of_people"
"
task_alias"
:
"
three
principles
of
people"
lm_eval/tasks/tmmluplus/default/tmmluplus_trade.yaml
0 → 100644
View file @
60c9c170
"
dataset_name"
:
"
trade"
"
description"
:
"
以下為貿易的單選題,請提供正確答案的選項。
\n\n
"
"
group"
:
"
tmmluplus_other"
"
group_alias"
:
"
other"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
tmmluplus_trade"
"
task_alias"
:
"
trade"
lm_eval/tasks/tmmluplus/default/tmmluplus_traditional_chinese_medicine_clinical_medicine.yaml
0 → 100644
View file @
60c9c170
"
dataset_name"
:
"
traditional_chinese_medicine_clinical_medicine"
"
description"
:
"
以下為中醫臨床醫學的單選題,請提供正確答案的選項。
\n\n
"
"
group"
:
"
tmmluplus_other"
"
group_alias"
:
"
other"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
tmmluplus_traditional_chinese_medicine_clinical_medicine"
"
task_alias"
:
"
traditional
chinese
medicine
clinical
medicine"
lm_eval/tasks/tmmluplus/default/tmmluplus_trust_practice.yaml
0 → 100644
View file @
60c9c170
"
dataset_name"
:
"
trust_practice"
"
description"
:
"
以下為信託實務的單選題,請提供正確答案的選項。
\n\n
"
"
group"
:
"
tmmluplus_humanities"
"
group_alias"
:
"
humanities"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
tmmluplus_trust_practice"
"
task_alias"
:
"
trust
practice"
lm_eval/tasks/tmmluplus/default/tmmluplus_ttqav2.yaml
0 → 100644
View file @
60c9c170
"
dataset_name"
:
"
ttqav2"
"
description"
:
"
以下為台灣在地用語的單選題,請提供正確答案的選項。
\n\n
"
"
group"
:
"
tmmluplus_social_sciences"
"
group_alias"
:
"
social
sciences"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
tmmluplus_ttqav2"
"
task_alias"
:
"
ttqav2"
lm_eval/tasks/tmmluplus/default/tmmluplus_tve_chinese_language.yaml
0 → 100644
View file @
60c9c170
"
dataset_name"
:
"
tve_chinese_language"
"
description"
:
"
以下為統測國文的單選題,請提供正確答案的選項。
\n\n
"
"
group"
:
"
tmmluplus_social_sciences"
"
group_alias"
:
"
social
sciences"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
tmmluplus_tve_chinese_language"
"
task_alias"
:
"
tve
chinese
language"
lm_eval/tasks/tmmluplus/default/tmmluplus_tve_design.yaml
0 → 100644
View file @
60c9c170
"
dataset_name"
:
"
tve_design"
"
description"
:
"
以下為統測
設計的單選題,請提供正確答案的選項。
\n\n
"
"
group"
:
"
tmmluplus_other"
"
group_alias"
:
"
other"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
tmmluplus_tve_design"
"
task_alias"
:
"
tve
design"
lm_eval/tasks/tmmluplus/default/tmmluplus_tve_mathematics.yaml
0 → 100644
View file @
60c9c170
"
dataset_name"
:
"
tve_mathematics"
"
description"
:
"
以下為統測數學的單選題,請提供正確答案的選項。
\n\n
"
"
group"
:
"
tmmluplus_STEM"
"
group_alias"
:
"
STEM"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
tmmluplus_tve_mathematics"
"
task_alias"
:
"
tve
mathematics"
lm_eval/tasks/tmmluplus/default/tmmluplus_tve_natural_sciences.yaml
0 → 100644
View file @
60c9c170
"
dataset_name"
:
"
tve_natural_sciences"
"
description"
:
"
以下為統測自然科的單選題,請提供正確答案的選項。
\n\n
"
"
group"
:
"
tmmluplus_STEM"
"
group_alias"
:
"
STEM"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
tmmluplus_tve_natural_sciences"
"
task_alias"
:
"
tve
natural
sciences"
lm_eval/tasks/tmmluplus/default/tmmluplus_veterinary_pathology.yaml
0 → 100644
View file @
60c9c170
"
dataset_name"
:
"
veterinary_pathology"
"
description"
:
"
以下為獸醫病理學的單選題,請提供正確答案的選項。
\n\n
"
"
group"
:
"
tmmluplus_other"
"
group_alias"
:
"
other"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
tmmluplus_veterinary_pathology"
"
task_alias"
:
"
veterinary
pathology"
lm_eval/tasks/tmmluplus/default/tmmluplus_veterinary_pharmacology.yaml
0 → 100644
View file @
60c9c170
"
dataset_name"
:
"
veterinary_pharmacology"
"
description"
:
"
以下為獸醫藥理學的單選題,請提供正確答案的選項。
\n\n
"
"
group"
:
"
tmmluplus_other"
"
group_alias"
:
"
other"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
tmmluplus_veterinary_pharmacology"
"
task_alias"
:
"
veterinary
pharmacology"
lm_eval/tasks/tmmluplus/default/utils.py
0 → 100644
View file @
60c9c170
import
datasets
def
process_docs
(
dataset
:
datasets
.
Dataset
)
->
datasets
.
Dataset
:
def
_helper
(
doc
):
# modifies the contents of a single
# document in our dataset.
answer_list
=
[
"A"
,
"B"
,
"C"
,
"D"
]
out_doc
=
{
"questions"
:
doc
[
"question"
],
"choices"
:
[
doc
[
"A"
],
doc
[
"B"
],
doc
[
"C"
],
doc
[
"D"
]],
"goal"
:
answer_list
.
index
(
doc
[
"answer"
]),
}
return
out_doc
return
dataset
.
map
(
_helper
)
# returns back a datasets.Dataset object
Prev
1
…
24
25
26
27
28
29
30
31
Next
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment